AIP Question Bank · Latest 50 Questions Free Preview (Page 1/5)

Questions 1–10 of the latest 50 AIP questions (5 pages total), with answers and explanations, no login required. Practice all 98 questions online.

Question 1 · No. 48 · Single choice

A company is developing a generative AI (GenAI) application that analyzes customer service calls in real-time and generates suggested responses for human customer service agents. The application must process 500,000 concurrent calls during peak hours with less than 200 ms end-to-end latency for each suggestion. The company uses existing architecture to transcribe customer call audio streams. The application must not exceed a pre-defined monthly compute budget and must maintain auto scaling capabilities. Which solution will meet these requirements?

A. Deploy a large, complex reasoning model on Amazon Bedrock. Purchase provisioned throughput and optimize for batch processing.
B. Deploy a low-latency, real-time optimized model on Amazon Bedrock. Purchase provisioned throughput and set up automatic scaling policies.
C. Deploy a large language model (LLM) on an Amazon SageMaker AI real-time endpoint that uses dedicated GPU instances.
D. Deploy a mid-sized language model on an Amazon SageMaker AI serverless endpoint that is optimized for batch processing.

Answer: B

Explanation: Option B is the best choice because it directly addresses all the key requirements: (1) A low-latency, real-time optimized model meets the <200ms end-to-end latency requirement for real-time suggestion generation; (2) Provisioned throughput provides cost predictability which helps stay within the monthly compute budget; (3) Automatic scaling policies handle the 500,000 concurrent calls during peak hours. Option A uses a large reasoning model optimized for batch processing, which would not meet the real-time latency requirement. Option C uses dedicated GPU instances which are expensive and harder to auto-scale, potentially exceeding the budget. Option D uses batch processing optimization which fails the real-time latency requirement. Amazon Bedrock with provisioned throughput and auto scaling offers the optimal balance of performance, cost control, and scalability for this use case.

Question 2 · No. 49 · Single choice

A large ecommerce company has deployed a foundation model (FM) to generate product descriptions. The company's engineering team monitors technical metrics such as token usage, latency, and error rates by using Amazon CloudWatch. The company's marketing team tracks business metrics such as conversion rates and revenue impact in its own systems. The company needs a unified observability solution that correlates technical performance with business outcomes. The solution must provide automatic alerts to stakeholders when operational metrics indicate degradation. The solution must provide comprehensive visibility across both technical and business metrics. Which solution will meet these requirements?

A. Create CloudWatch dashboards that include technical metrics and imported business metrics. Configure CloudWatch composite alarms that combine technical data and business data. Use Amazon SNS to set up notifications to stakeholders.
B. Use Amazon Managed Grafana to visualize technical metrics from CloudWatch with business metrics from external sources. Configure Amazon Managed Grafana alerts to invoke AWS Lambda functions. Configure the Lambda functions to remediate issues automatically when metrics exceed predefined thresholds.
C. Stream CloudWatch metrics to Amazon S3 by using CloudWatch metric streams. Create Amazon QuickSight dashboards to visualize the combined technical metrics and business metrics. Set up Amazon EventBridge rules to send notifications to stakeholders when metrics exceed predefined thresholds.
D. Configure CloudWatch custom dashboards that integrate operational metrics with imported business metrics. Set up CloudWatch composite alarms with anomaly detection. Use Amazon SNS to create alarm actions to notify stakeholders when correlated metrics indicate performance issues.

Answer: D

Question 3 · No. 50 · Single choice

A university recently digitized a collection of archival documents, academic journals, and manuscripts. The university stores the digital files in an AWS Lake Formation data lake. The university hires a GenAI developer to build a solution to allow users to search the digital files by using text queries. The solution must return journal abstracts that are semantically similar to a user's query. Users must be able to search the digitized collection based on text and metadata that is associated with the journal abstracts. The metadata of the digitized files does not contain keywords. The solution must match similar abstracts to one another based on the similarity of their text. The data lake contains fewer than 1 million files. Which solution will meet these requirements with the LEAST operational overhead?

A. Use Amazon Titan Embeddings in Amazon Bedrock to create vector representations of the digitized files. Store embeddings in the OpenSearch Neural Plugin for Amazon OpenSearch Service.
B. Use Amazon Comprehend to extract topics from the digitized files. Store the topics and file metadata in an Amazon Aurora PostgreSQL database. Query the abstract metadata against the data in the Aurora database.
C. Use Amazon SageMaker AI to deploy a sentence-transformer model. Use the model to create vector representations of the digitized files. Store embeddings in an Amazon Aurora PostgreSQL database that has the pgvector extension.
D. Use Amazon Titan Embeddings in Amazon Bedrock to create vector representations of the digitized files. Store embeddings in an Amazon Aurora PostgreSQL Serverless database that has the pgvector extension.

Answer: D

Question 4 · No. 51 · Single choice

A company is using Amazon Bedrock to develop a customer support AI assistant. The AI assistant must respond to customer questions about their accounts. The AI assistant must not expose personal information in responses. The company must comply with data residency policies by ensuring that all processing occurs within the same AWS Region where each customer is located. The company wants to evaluate how effective the AI assistant is at preventing the exposure of personal information before the company makes the AI assistant available to customers. Which solution will meet these requirements?

A. Configure a cross-Region Amazon Bedrock guardrail to apply sensitive information filters. Set the guardrail to detect mode during development and testing. Switch to block mode for production deployment.
B. Configure an Amazon Bedrock guardrail to apply sensitive information filters. Set the guardrail to mask mode during development and testing. Switch to block mode for production deployment. Deploy a copy of the guardrail to each Region where the company operates.
C. Configure an Amazon Bedrock guardrail to apply content and topic filters. Set the guardrail to detect mode during development, testing, and production. Disable invocation logging for the Amazon Bedrock model.
D. Configure a cross-Region Amazon Bedrock guardrail to apply a set of content and word filters. Set the guardrail to detect mode during development and testing. Switch to mask mode for production deployment.

Answer: B

Explanation: Option B is correct because it satisfies all the requirements: (1) It uses Amazon Bedrock guardrails with sensitive information filters, which are specifically designed to prevent the exposure of PII. (2) Using 'mask mode' during development and testing allows the company to evaluate how effective the guardrail is at identifying and masking PII without blocking responses, enabling proper evaluation before production. (3) Deploying a copy of the guardrail to each Region where the company operates ensures data residency compliance, as all processing occurs within the same AWS Region as the customer. (4) Switching to 'block mode' for production provides stronger protection by actively blocking any responses containing PII. Option A uses a cross-Region guardrail which violates data residency. Option C uses content/topic filters (not sensitive information filters) and disables logging, preventing proper evaluation. Option D also uses cross-Region guardrails (violating data residency) and uses word filters rather than sensitive information filters.

Question 5 · No. 52 · Single choice

A company uses AWS Lake Formation to set up a data lake that contains databases and tables for multiple business units across multiple AWS Regions. The company wants to use a foundation model (FM) through Amazon Bedrock to perform fraud detection. The FM must ingest sensitive financial data from the data lake. The data includes some customer personally identifiable information (PM). The company must design an access control solution that prevents PI I from appearing in a production environment. The FM must access only authorized data subsets that have PH redacted from specific data columns. The company must capture audit trails for all data access. Which solution will meet these requirements?

A. Create a separate dataset in a separate Amazon S3 bucket for each business unit and Region combination. Configure S3 bucket policies to control access based on IAM roles that are assigned to FM training instances. Use S3 access logs to track data access.
B. Configure the FM to authenticate by using IAM roles and Lake Formation permissions based on LF-Tag expressions. Define business units and Regions as LF-Tags that are assigned to databases and tables. Use AWS CloudTrail to collect comprehensive audit trails of data access.
C. Use direct IAM principal grants on specific databases and tables in Lake Formation. Create a custom application layer that logs access requests and further filters sensitive columns before sending data to the FM.
D. Configure the FM to request temporary credentials from AWS STS. Access the data by using presigned S3 URLs that are generated by an API that applies business unit and Regional filters. Use AWS CloudTrail to collect comprehensive audit trails of data access.

Answer: B

Explanation: Option B is the best solution because Lake Formation with LF-Tag expressions provides attribute-based access control (ABAC) that scales well across multiple business units and Regions. LF-Tags can be assigned to databases and tables based on business units and Regions, allowing fine-grained, tag-based access control. Lake Formation natively supports column-level security, which is essential for redacting PII from specific data columns. Additionally, CloudTrail provides comprehensive audit trails for all data access, meeting the compliance and monitoring requirements. Option A uses S3 bucket policies but cannot handle column-level PII redaction and is not scalable. Option C requires custom application development which is less maintainable. Option D uses presigned URLs and STS but does not provide native column-level security or Lake Formation integration.

Question 6 · No. 53 · Single choice

A specialty coffee company has a mobile app that generates personalized coffee roast profiles by using Amazon Bedrock with a three-stage prompt chain. The prompt chain converts user inputs into structured metadata, retrieves relevant logs for coffee roasts, and generates a personalized roast recommendation for each customer. Users in multiple AWS Regions report inconsistent roast recommendations for identical inputs, slow inference during the retrieval step, and unsafe recommendations such as brewing at excessively high temperatures. The company must improve the stability of outputs for repeated inputs. The company must also improve app performance and the safety of the app's outputs. The updated solution must ensure 99.5% output consistency for identical inputs and achieve inference latency of less than 1 second. The solution must also block unsafe or hallucinated recommendations by using validated safety controls. Which solution will meet these requirements?

A. Deploy Amazon Bedrock with provisioned throughput to stabilize inference latency. Apply Amazon Bedrock guardrails that have semantic denial rules to block unsafe outputs. Use Amazon Bedrock Prompt Management to manage prompts by using approval workflows.
B. Use Amazon Bedrock Agents to manage chaining. Log model inputs and outputs to Amazon CloudWatch Logs. Use logs from Amazon CloudWatch to perform A/B testing for prompt versions.
C. Cache prompt results in Amazon ElastiCache. Use AWS Lambda functions to pre-process metadata and to trace end-to-end latency. Use AWS X-Ray to identify and remediate performance bottlenecks.
D. Use Amazon Kendra to improve roast log retrieval accuracy. Store normalized prompt metadata within Amazon DynamoDB. Use AWS Step Functions to orchestrate multistep prompts.

Answer: A

Explanation: Option A is the correct solution because it directly addresses all three requirements. First, Amazon Bedrock with provisioned throughput stabilizes inference latency by reserving dedicated capacity, which ensures consistent sub-1-second response times. Second, Amazon Bedrock guardrails with semantic denial rules block unsafe outputs (such as excessive brewing temperatures) and hallucinated recommendations, meeting the safety requirement. Third, Amazon Bedrock Prompt Management with approval workflows ensures version control and consistency of prompts across regions, achieving the 99.5% output consistency for identical inputs. The other options fail to comprehensively address all requirements: Option B focuses on logging and A/B testing but lacks specific safety controls and latency stabilization mechanisms; Option D improves retrieval but does not provide latency guarantees or safety controls; Option C improves performance monitoring but lacks dedicated safety mechanisms for blocking unsafe outputs.

Question 7 · No. 54 · Multiple choice

A company uses an organization in AWS Organizations with all features enabled to manage multiple AWS accounts. Employees use Amazon Bedrock across multiple accounts. The company must prevent specific topics and proprietary information from being included in prompts to Amazon Bedrock models. The company must ensure that employees can use only approved Amazon Bedrock models. The company centrally manages IAM roles for employees. Which combination of solutions will meet these requirements? (Choose two.)

A. Create an IAM permissions boundary for each employee's IAM role. Configure the permissions boundary to require an approved Amazon Bedrock guardrail identifier to invoke Amazon Bedrock models. Create an SCP that allows employees to use only approved models.
B. Create an SCP that allows employees to use only approved models. Configure the SCP to require employees to specify a guardrail identifier in calls to invoke an approved model.
C. Create an SCP that prevents an employee from invoking a model if a centrally deployed guardrail identifier is not specified in a call to the model. Create a permissions boundary on each employee's IAM role that allows each employee to invoke only approved models.
D. Use AWS CloudFormation to create a custom Amazon Bedrock guardrail that has a block filtering policy. Use stack sets to deploy the guardrail to each account in the organization.
E. Use AWS CloudFormation to create a custom Amazon Bedrock guardrail that has a mask filtering policy. Use stack sets to deploy the guardrail to each account in the organization.

Answer: B, D

Question 8 · No. 55 · Single choice

A wildlife conservation agency operates zoos globally. The agency uses various sensors, trackers, and audiovisual recorders to monitor animal behavior. The agency wants to launch a generative AI (GenAI) assistant that can ingest multimodal data to study animal behavior. The GenAI assistant must support natural language queries, avoid speculative behavioral interpretations, and maintain audit logs for ethical research audits. Which solution will meet these requirements?

A. Ingest raw videos into Amazon Rekognition to detect animal postures and expressions. Use Amazon Data Firehose to stream sensor and GPS data into an Amazon S3 data lake. Prompt an Amazon Bedrock foundation model (FM) by using basic templates that are stored in AWS Systems Manager Parameter Store. Use IAM policies to control access. Use AWS CloudTrail for audit logging.
B. Use Amazon SageMaker Processing and Amazon Transcribe to pre-process multimodal data. Ingest summaries into an Amazon Bedrock Retrieval Augmented Generation (RAG) knowledge base. Apply Amazon Bedrock guardrails to restrict speculative outputs. Use AWS AppConfig to manage prompt templates. Use AWS CloudTrail to log research activity for audits.
C. Use Amazon OpenSearch Serverless to index behavioral logs and telemetry events. Use Amazon Comprehend to extract entities. Use Amazon Bedrock to build a layer to answer questions. Embed study summaries into OpenSearch Serverless documents. Use IAM to control access. Use AWS CloudTrail to log user interactions with the AI assistant.
D. Configure Amazon Q Business to federate data across Amazon S3, Amazon Kinesis, and Amazon SageMaker Feature Store. Configure Amazon EventBridge to invoke data ingestion jobs. Use custom AWS Lambda functions to filter large language model (LLM) outputs for ethical compliance before returning results to users.

Answer: B

Explanation: Option B is the best choice because it directly addresses all four requirements: (1) Multimodal data ingestion - SageMaker Processing and Amazon Transcribe handle preprocessing of multimodal data; (2) Natural language queries - Bedrock RAG knowledge base supports this; (3) Avoids speculative interpretations - Amazon Bedrock guardrails specifically restrict speculative outputs; (4) Audit logs - CloudTrail logs research activity. Option A lacks guardrails for preventing speculative outputs. Option C doesn't address preventing speculative outputs. Option D uses custom Lambda filtering instead of native Bedrock guardrails, which is less efficient, and doesn't address multimodal data ingestion comprehensively.

Question 9 · No. 56 · Single choice

A company uses Amazon Bedrock to implement a Retrieval Augmented Generation (RAG)-based system to serve medical information to users. The company needs to compare multiple chunking strategies, evaluate the generation quality of two foundation models (FMs), and enforce quality thresholds for deployment. Which Amazon Bedrock evaluation configuration will meet these requirements?

A. Create a retrieve-only evaluation job that uses a supported version of Anthropic Claude Sonnet as the evaluator model. Configure metrics for context relevance and context coverage. Define deployment thresholds in a separate CI/CD pipeline.
B. Create a retrieve-and-generate evaluation job that uses custom precision at k metrics and an LLM-as-a-judge metric that uses a scale of 1-5. Include each chunking strategy in the evaluation dataset. Use a supported version of Anthropic Claude Sonnet to evaluate responses from both FMs.
C. Create a separate evaluation job for each chunking strategy and FM combination. Use Amazon Bedrock built-in metrics for correctness and completeness. Manually review scores before deployment approval.
D. Set up a pipeline that uses multiple retrieve-only evaluation jobs to assess retrieval quality. Create separate evaluation jobs for both FMs that use Amazon Nova Pro as the LLM-as-a-judge model. Evaluate based on faithfulness and citation precision metrics.

Answer: B

Explanation: Option B is the correct choice because it addresses all three requirements: 1) It uses a retrieve-and-generate evaluation job, which evaluates both retrieval and generation quality, unlike options A and D that only evaluate retrieval. 2) It includes each chunking strategy in the evaluation dataset, allowing direct comparison of multiple chunking strategies. 3) It uses Claude Sonnet as the evaluator model to evaluate responses from both foundation models, enabling comparison of generation quality between the two FMs. 4) The LLM-as-a-judge metric with a 1-5 scale allows for setting and enforcing quality thresholds for deployment. Option C creates inefficient separate jobs and relies on manual review rather than enforced thresholds. Options A and D only evaluate retrieval quality, not generation quality of the two FMs.

Question 10 · No. 57 · Single choice

A company is building a serverless application that uses AWS Lambda functions to help students around the world summarize notes. The application uses Anthropic Claude through Amazon Bedrock. The company observed that most of the traffic occurs during evenings in each time zone. Users report experiencing throttling errors during peak usage times in their times zones. The company needs to resolve the throttling issues by ensuring continuous operation of the application. The solution must maintain application performance quality. The company needs a solution that does not require a fixed hourly cost during low traffic periods. Which solution will meet these requirements?

A. Create custom Amazon CloudWatch metrics to monitor model errors. Set provisioned throughput to a value that is safely higher than the peak traffic observed.
B. Create custom Amazon CloudWatch metrics to monitor model errors. Set up a failover mechanism to redirect invocations to a backup AWS Region when the errors exceed a specified threshold.
C. Enable invocation logging in Amazon Bedrock. Monitor key metrics such as Invocations, InputTokenCount, OutputTokenCount, and Invocation Throttles. Distribute traffic across cross-Region inference endpoints.
D. Enable invocation logging in Amazon Bedrock. Monitor InvocationLatency, InvocationClientErrors, and InvocationServerErrors metrics. Distribute traffic across multiple versions of the same model.

Answer: C

Explanation: Option C is the best solution because it directly addresses the throttling issue with the InvocationThrottles metric and uses cross-Region inference endpoints to distribute traffic. Since the company has globally distributed users with peak traffic occurring during evenings in different time zones, cross-Region distribution effectively balances load and prevents throttling in any single region. This solution uses on-demand pricing without fixed hourly costs during low traffic periods, maintaining application performance quality. Option A uses provisioned throughput which has fixed hourly costs. Option B's failover mechanism is reactive rather than proactive and uses less appropriate metrics. Option D's multiple model versions don't address throttling capacity issues.

12 3 4 5 Next